Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1814 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.5924. Min Act: -0.0000

Data Index: 761739 (The Pile)

Max Activating Token Index: 539

Text #1

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.5711. Min Act: -0.0000

Data Index: 37081 (The Pile)

Max Activating Token Index: 343

Text #2

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.5436. Min Act: -0.0000

Data Index: 1092120 (The Pile)

Max Activating Token Index: 465

Text #3

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.5349. Min Act: -0.0000

Data Index: 786981 (The Pile)

Max Activating Token Index: 936

Text #4

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.5240. Min Act: -0.0000

Data Index: 1908344 (The Pile)

Max Activating Token Index: 865

Text #5

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.5395. Min Act: -0.0000

Data Index: 225300 (The Pile)

Max Activating Token Index: 507

Text #6

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.5023. Min Act: -0.0000

Data Index: 1117457 (The Pile)

Max Activating Token Index: 350

Text #7

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4748. Min Act: -0.0000

Data Index: 210327 (The Pile)

Max Activating Token Index: 718

Text #8

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.5168. Min Act: -0.0000

Data Index: 159751 (The Pile)

Max Activating Token Index: 246

Text #9

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.5181. Min Act: -0.0000

Data Index: 479813 (The Pile)

Max Activating Token Index: 976

Text #10

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4360. Min Act: -0.0000

Data Index: 1304165 (The Pile)

Max Activating Token Index: 994

Text #11

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4607. Min Act: -0.0000

Data Index: 643417 (The Pile)

Max Activating Token Index: 295

Text #12

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4732. Min Act: -0.0000

Data Index: 406359 (The Pile)

Max Activating Token Index: 866

Text #13

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.5043. Min Act: -0.0000

Data Index: 617936 (The Pile)

Max Activating Token Index: 368

Text #14

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4755. Min Act: -0.0000

Data Index: 1636216 (The Pile)

Max Activating Token Index: 182

Text #15

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4626. Min Act: -0.0000

Data Index: 570206 (The Pile)

Max Activating Token Index: 740

Text #16

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4168. Min Act: -0.0000

Data Index: 460927 (The Pile)

Max Activating Token Index: 789

Text #17

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4585. Min Act: -0.0000

Data Index: 1144584 (The Pile)

Max Activating Token Index: 446

Text #18

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4684. Min Act: -0.0000

Data Index: 430417 (The Pile)

Max Activating Token Index: 756

Text #19

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4819. Min Act: -0.0000

Data Index: 200002 (The Pile)

Max Activating Token Index: 416